How enabling two settings tripled our scores on the ARC-AGI-3 benchmark [LAB]
OpenAI researchers demonstrate how specific API tuning significantly boosts reasoning performance on complex benchmarks. https://openai.com/index/how-two-settings-tripled-our-arc-agi-3-scores (openai.com)
How GPT-5.6 fuses frontier intelligence with frontier efficiency [LAB]
This technical update details improvements in model efficiency and agentic workflows for the next generation of AI intelligence. https://openai.com/index/gpt-5-6-frontier-intelligence-efficiency (openai.com)